CN108921004A - Safety cap wears recognition methods, electronic equipment, storage medium and system - Google Patents
Safety cap wears recognition methods, electronic equipment, storage medium and system Download PDFInfo
- Publication number
- CN108921004A CN108921004A CN201810392822.7A CN201810392822A CN108921004A CN 108921004 A CN108921004 A CN 108921004A CN 201810392822 A CN201810392822 A CN 201810392822A CN 108921004 A CN108921004 A CN 108921004A
- Authority
- CN
- China
- Prior art keywords
- safety cap
- image
- human
- region
- wears
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of safety cap wearing recognition methods, including Image Acquisition, is acquired to area image to be measured；Foreground detection processing is carried out to the area image to be measured using mixed Gauss model and obtains the binary image of foreground area in the region to be measured, the binary image is subjected to human figure differentiation processing and obtains human geometry's appearance model；According to the positional relationship of human body safe wearing cap, safety cap wears region in the position in human geometry's appearance model, extracts the pixel characteristic that the safety cap wears region；The pixel characteristic for wearing region to the safety cap differentiates with default safety cap feature, if meeting default safety cap feature, is determined as safe wearing cap, if not satisfied, being then determined as non-safe wearing cap.Safety cap of the invention wear recognition methods by automatic identification construction personnel whether safe wearing cap, save monitoring expense, complete monitoring can be carried out to the construction personnel in the region of construction site.
Description
Technical field
The present invention relates to safety precaution field more particularly to safety cap wear recognition methods, electronic equipment, storage medium and
System.
Background technique
With China's expanding economy, the construction of various infrastructures and urban construction is more and more, pacifies in construction area
It is complete as first criterion, supervision departments and unit in charge of construction at different levels are also that the safety of construction personnel is put in the first place, are being constructed
Area, safety cap can be effectively prevented and mitigate foreign dangers source enemy as a kind of most common and practical personal shield apparatus
The injury in portion.However, for a long time, China construction area generally existing overall qualities of operating personnel are low, awareness of safety is not strong asks
Topic, especially the wearing consciousness of shortage foundation protection facility (such as safety cap), considerably increase operating risk.Currently, construction site
To the identification of safety cap wear condition mainly in a manner of manual inspection based on, that there are oversight costs is high for the mode of manual inspection,
Subjectivity interference is big, is unable to the problems such as complete monitoring.
Summary of the invention
For overcome the deficiencies in the prior art, one of the objects of the present invention is to provide safety caps to wear recognition methods,
The mode that can solve manual inspection has that oversight costs are high, subjective interference is big, are unable to complete monitoring.
The second purpose of invention is to provide a kind of electronic equipment, and can solve the mode of manual inspection, there are oversight costs
High, subjective interference is big, is unable to the problem of complete monitoring.
The third purpose of invention is to provide a kind of storage medium, and can solve the mode of manual inspection, there are oversight costs
High, subjective interference is big, is unable to the problem of complete monitoring.
The fourth purpose of invention is that providing safe hair wears identifying system, and the mode that can solve manual inspection has prison
Manage that costly, subjective interference is big, is unable to the problem of complete monitoring.
An object of the present invention is implemented with the following technical solutions：
Safety cap wears recognition methods, including：
Image Acquisition is acquired area image to be measured；
It determines human geometry's form, foreground detection processing is carried out simultaneously to the area image to be measured using mixed Gauss model
The binary image of foreground area in the region to be measured is obtained, the binary image is subjected to human figure differentiation processing simultaneously
Obtain human geometry's appearance model；
Pixel characteristic is extracted, according to position of the positional relationship of human body safe wearing cap in human geometry's appearance model
It sets middle safety cap and wears region, extract the pixel characteristic that the safety cap wears region；
Safety cap wears identification, and the pixel characteristic for wearing region to the safety cap is sentenced with default safety cap feature
Not, if meeting default safety cap feature, it is determined as safe wearing cap, if not satisfied, being then determined as non-safe wearing cap.
It further, further include image preprocessing before determining human geometry's form, to the area image to be measured
Carry out image gray processing processing and image denoising processing.
Further, determining human geometry's form specifically includes：
Display foreground detection, each pixel in the area image to be measured is matched with Gauss model and obtains background
Point obtains the binary image about foreground area in the region to be measured according to the background dot；
Human figure differentiates；The binary image is successively subjected to graphics expansion processing, edge detection process and people
Body identifying processing obtains human geometry's appearance model.
It further, further include that the binary picture is rejected using the method for median filtering before the human figure differentiates
Noise as in.
Further, the edge detection process is specifically included using Canny edge detection algorithm to the binary picture
Human region as in carries out edge detection.
The second object of the present invention is implemented with the following technical solutions：
A kind of electronic equipment, including：Processor；
Memory；And program, wherein described program is stored in the memory, and is configured to by processor
It executes, described program includes wearing recognition methods for executing safety cap of the invention.
The third object of the present invention is implemented with the following technical solutions：
A kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that：The computer program
It is executed by processor safety cap of the invention and wears recognition methods.
The fourth object of the present invention is implemented with the following technical solutions：
Safety cap wears identifying system, it is characterised in that including：
Acquisition module, the acquisition module is for being acquired area image to be measured；
Human geometry's form determining module, human geometry's body determining module are used for using mixed Gauss model to institute
Area image to be measured is stated to carry out foreground detection processing and obtain the binary image of foreground area in the region to be measured, it will be described
Binary image carries out human figure and differentiates processing and obtain human geometry's appearance model；
Pixel characteristic extraction module, the pixel characteristic extraction module are used for the positional relationship according to human body safe wearing cap
Safety cap wears region in the position in human geometry's appearance model, extracts the pixel spy that the safety cap wears region
Sign；
Safety cap wears identification module, and the safety cap wears the picture that identification module is used to wear the safety cap region
Plain feature is differentiated with default safety cap feature, if meeting default safety cap feature, is determined as safe wearing cap, if not
Meet, is then determined as non-safe wearing cap.
It further, further include image pre-processing module, described image preprocessing module is used for the administrative division map to be measured
As carrying out image gray processing processing and image denoising processing.
Further, human geometry's form determining module includes that display foreground detection unit and human figure differentiate
Unit, described image foreground detection unit is for matching simultaneously each pixel in the area image to be measured with Gauss model
Background dot is obtained, the binary image about foreground area in the region to be measured is obtained according to the background dot；The human body
Morphological Identification unit is used to the binary image successively carrying out graphics expansion processing, edge detection process and human bioequivalence
Processing, obtains human geometry's appearance model.
Compared with prior art, the beneficial effects of the present invention are：Safety cap of the invention wears recognition methods, by treating
It surveys area image to be acquired, foreground detection processing is carried out to area image to be measured using mixed Gauss model and obtains area to be measured
Binary image is carried out human figure differentiation processing and obtains human geometry's form mould by the binary image of foreground area in domain
Type, according to the positional relationship of human body safe wearing cap, safety cap wears region in the position in human geometry's appearance model, mentions
Safety cap is taken to wear the pixel characteristic in region；The pixel characteristic for wearing region to safety cap is sentenced with default safety cap feature
Not, if meeting default safety cap feature, it is determined as safe wearing cap, if not satisfied, being then determined as non-safe wearing cap；This
Kind is acquired using acquisition area image to be measured and by extracting human geometry's form and determining that safety cap wears region,
Determine that safety cap wears whether region meets default safety cap feature, again so as to automatically identify applying in region to be measured
Worker person whether safe wearing cap, it is no longer necessary to manually checked, and the construction that this automatic identification in the application adapts to
Environment is varied, and the environmental suitability with height saves monitoring expense, can be to the constructor in the region of construction site
Member carries out complete monitoring, avoids security risk caused by missing inspection, improves the safety of construction personnel itself.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And can be implemented in accordance with the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention and the accompanying drawings.
A specific embodiment of the invention is shown in detail by following embodiment and its attached drawing.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings：
Fig. 1 is the flow chart that safety cap of the invention wears recognition methods；
Fig. 2 is the system block diagram that safety cap of the invention wears identifying system.
Specific embodiment
In the following, being described further in conjunction with attached drawing and specific embodiment to the present invention, it should be noted that not
Under the premise of conflicting, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
It is existing applied to the various constructions for needing construction personnel's safe wearing cap that safety cap in the application wears recognition methods
, include the following steps as shown in Figure 1, the safety cap of the application wears recognition methods：
Setting needs the construction area detected, and for improving image processing speed, what the needs set herein detected is applied
Work area domain is region to be measured；
It carries out image to area to be tested to be acquired, using existing video monitoring equipment to the image of area to be tested
It carries out Image Acquisition and obtains area image to be measured；
Image preprocessing is carried out to area image to be measured, color image information is commonly to construction area acquired image,
To improve image processing speed, image preprocessing need to be carried out to area image to be measured, image preprocessing includes to administrative division map to be measured
As carrying out image gray processing processing and image denoising processing, specially：It is advanced to area image to be measured using weighted mean method
The processing of row gray processing, by R, tri- components of G, B are weighted and averaged with different weights, specific weighted average formula such as formula
(1) shown in：
F (i, j)=0.30R (i, j)+0.59G (i, j)+0.11B (i, j) (1)
In formula (1)：F (i, j) is gray processing result；R (i, j) is red channel color variance, and G (i, j) is green
Channel color variance, B (i, j) are blue channel color variance.
Image denoising processing is carried out to area image to be measured, is removed by the way of median filtering in area image to be measured
Noise spot；Median filtering method is a kind of nonlinear smoothing technology, sets the point neighborhood window for the gray value of each pixel
The intermediate value of all pixels point gray value in mouthful.The two-dimentional sleiding form of median filtering method, pixel value in plate is sorted by size,
Generate the 2-D data sequence of monotone increasing (or decline).
Determine that human geometry's form, including display foreground detection and human figure differentiate that display foreground detection specifically includes：
Foreground detection processing is carried out to area image to be measured using mixed Gauss model and obtains the two-value of foreground area in region to be measured
Change image, the feature of each pixel in area image to be measured is characterized using 6 Gauss models, after the acquisition of new frame image
Mixed Gauss model is updated, is matched with each pixel in present image with mixed Gauss model, if successful match, is sentenced
The fixed point is background dot, is otherwise foreground point, to obtain background dot, is obtained according to background dot about foreground zone in region to be measured
The binary image in domain carries out noise points deleting processing using the method for median filtering to the binary image in foreground area.
Human figure identifies：Binary image is subjected to graphics expansion processing, image expansion processing is i.e. with structural element two
Moved on value image, if having in structural element a point with the point in image be it is Chong Die, to carrying out image expansion
Treated, and binary image carries out edge detection process, and the purpose of edge detection is to sketch the contours of the edge configuration of human body, uses
Canny edge detection algorithm carries out edge detection to the human region in binary image, specifically includes：It is 1.4 using variance
Gaussian function template and image carry out convolution algorithm, and then smoothed image removes picture noise point, calculate gradient amplitude and
When direction, and the replication application non-maxima suppression of gradient is adopted to make the marginal point of Canny operator extraction have more robustness
It is detected with dual threashold value-based algorithm and connects edge, it is assumed that high and low threshold value is respectively Hth and Lth, when choosing high threshold Hth, using figure
It is carried out as the corresponding histogram of gradient value.If non-edge point number accounts for total figure as pixel number purpose ratio is Hratio, root
It adds up according to the corresponding histogram of image gradient value, it, will be corresponding when accumulated amount reaches total pixel number purpose Hratio
Image gradient value is calculated as Hth.Low threshold Lth then passes through Lth=Hratio ﹡ Hth and is calculated.Finally by the mark to marginal point
Note and Domain relation are attached, and obtain edge detection graph, then use the method for model construction by the human body in binary image
The fitting that motion feature is embodied is to foundation and obtains corresponding human geometry's appearance model,
Pixel characteristic is extracted, according to the positional relationship of human body safe wearing cap in the position in human geometry's appearance model
Safety cap wears region, extracts the pixel characteristic that safety cap wears region.Specially：Shape based moment is constructed with human body edge periphery
Shape, it is desirable that bounding rectangles include all human body edges, using bounding rectangles top edge as the top edge of estimation rectangle, bounding rectangles
Top edge and following intermarginal 1/10 is used as estimation rectangle lower edge close to upper marginal position, and bounding rectangles left edge and the right are intermarginal
1/4 is used as estimation rectangle left edge close to left edge position, and bounding rectangles left edge and the right intermarginal 3/4 are close to right edge position
As estimation rectangle right hand edge, forms safety cap and estimate rectangle, is i.e. safety cap wears region；Safety cap is extracted to wear in region
Pixel characteristic.
Safety cap wears identification, and the pixel characteristic for wearing region to safety cap differentiates with default safety cap feature, if
Meet default safety cap feature, is then determined as safe wearing cap, if not satisfied, being then determined as non-safe wearing cap；Specially：
Obtain the triple channel pixel point value (i.e. R, G, B value) of the original color image of the pixel characteristic of safety cap wearing regional location, classification
The color category of the safety cap generallyd use at present includes commonly red, yellow, white three kinds of colors, according to the safety of different color
It is preset safety cap feature that cap, which establishes threshold value selection range, and each color-safe cap threshold contrast table is as shown in table 1：
The 1 safety cap color threshold table of comparisons of table
| Red safety cap | Yellow safety cap | White safety cap | |
| R | [160,200] | [205,255] | [205,255] |
| G | [15,75] | [160,220] | [205,255] |
| B | [0,50] | [0,50] | [205,255] |
The pixel in point-by-point statistics safety cap estimation region, if the R of pixel, G, B value is all satisfied safety cap color threshold
Certain safety cap color threshold range in the table of comparisons, then record the point, classify to all statistics points, and judgement is each
The quantity of kind safety cap color point accounts for the ratio of entire statistical regions pixel quantity, determines its wearing if being more than a certain ratio
The safety cap of corresponding color determines its non-safe wearing cap, construction personnel is determined if backlog demand if being all satisfied requirement
Safe wearing cap.
The second embodiment of the present invention provides a kind of electronic equipment, including：Processor；
Memory；And program, wherein program is stored in memory, and is configured to be executed by processor, journey
Sequence includes wearing recognition methods for executing safety cap of the present invention.
Third embodiment of the invention provides a kind of computer readable storage medium, is stored thereon with computer program, meter
Calculation machine program is executed by processor safety cap of the present invention and wears recognition methods.
The present invention also provides safety caps to wear identifying system, as shown in Fig. 2, safety cap wearing identifying system includes：It adopts
Collect module, acquisition module is for being acquired area image to be measured；Human geometry's form determining module, human geometry's body are true
Cover half block is used to carry out foreground detection processing to area image to be measured using mixed Gauss model and obtains prospect in region to be measured
Binary image is carried out human figure differentiation processing and obtains human geometry's appearance model by the binary image in region；Pixel
Characteristic extracting module, pixel characteristic extraction module are used for the positional relationship according to human body safe wearing cap in human geometry's form mould
Safety cap wears region in position in type, extracts the pixel characteristic that safety cap wears region；
Safety cap wear identification module, safety cap wear identification module be used for safety cap wear region pixel characteristic with
Default safety cap feature is differentiated, if meeting default safety cap feature, is determined as safe wearing cap, if not satisfied, then
It is determined as non-safe wearing cap.
It preferably, further include image pre-processing module, image pre-processing module is used to carry out image to area image to be measured
Gray processing processing and image denoising processing.Human geometry's form determining module includes display foreground detection unit and human body shape
State judgement unit, display foreground detection unit is for matching and obtaining each pixel in area image to be measured with Gauss model
To background dot, the binary image about foreground area in region to be measured is obtained according to background dot；Human figure judgement unit is used
In binary image successively to be carried out to graphics expansion processing, edge detection process and human bioequivalence processing, human geometry is obtained
Appearance model.
Safety cap of the invention wears recognition methods, by being acquired to area image to be measured, using mixed Gaussian mould
Type carries out foreground detection processing to area image to be measured and obtains the binary image of foreground area in region to be measured, by binaryzation
Image carries out human figure and differentiates processing and obtain human geometry's appearance model, is existed according to the positional relationship of human body safe wearing cap
Safety cap wears region in position in human geometry's appearance model, extracts the pixel characteristic that safety cap wears region；To safety
The pixel characteristic that cap wears region is differentiated with default safety cap feature, if meeting default safety cap feature, is determined as
Safe wearing cap, if not satisfied, being then determined as non-safe wearing cap；It is such to be acquired and lead to using acquisition area image to be measured
It crosses and extracts human geometry's form and determine that safety cap wears region, then determine that safety cap wears whether region meets default peace
Full cap feature, so as to automatically identify the construction personnel in region to be measured whether safe wearing cap, it is no longer necessary to it is artificial
It is checked, and the construction environment that this automatic identification in the application adapts to is varied, the environmental suitability with height,
Monitoring expense is saved, complete monitoring can be carried out to the construction personnel in the region of construction site, avoided caused by missing inspection
Security risk improves the safety of construction personnel itself.This method carries out foreground detection using mixed Gauss model, by right
The detection processing at connected region human body edge realizes the automatic discrimination to operating personnel and tracking, finally in estimation rectangle
Pixel is for statistical analysis, realizes the automatic identification detection of safety cap, this method has higher environmental suitability and detection is quasi-
True rate may be implemented the automatic identification detection to construction area operating personnel's safety cap wear condition, construction areas at different levels can be assisted to pacify
Full supervision unit carries out construction area intelligence supervision, improves the construction area security control level of IT application.
More than, only presently preferred embodiments of the present invention is not intended to limit the present invention in any form；All current rows
The those of ordinary skill of industry can be shown in by specification attached drawing and above and swimmingly implement the present invention；But all to be familiar with sheet special
The technical staff of industry without departing from the scope of the present invention, is made a little using disclosed above technology contents
The equivalent variations of variation, modification and evolution is equivalent embodiment of the invention；Meanwhile all substantial technologicals according to the present invention
The variation, modification and evolution etc. of any equivalent variations to the above embodiments, still fall within technical solution of the present invention
Within protection scope.
Claims (10)
1. safety cap wears recognition methods, it is characterised in that including：
Image Acquisition is acquired area image to be measured；
It determines human geometry's form, foreground detection processing is carried out to the area image to be measured using mixed Gauss model and obtains
The binary image is carried out human figure differentiation processing and obtained by the binary image of foreground area in the region to be measured
Human geometry's appearance model；
Pixel characteristic is extracted, according to the positional relationship of human body safe wearing cap in the position in human geometry's appearance model
Safety cap wears region, extracts the pixel characteristic that the safety cap wears region；
Safety cap wears identification, and the pixel characteristic for wearing region to the safety cap differentiates with default safety cap feature, if
Meet default safety cap feature, is then determined as safe wearing cap, if not satisfied, being then determined as non-safe wearing cap.
2. safety cap as described in claim 1 wears recognition methods, it is characterised in that：Before determining human geometry's form
Further include image preprocessing, image gray processing processing is carried out to the area image to be measured and image denoising is handled.
3. safety cap as described in claim 1 wears recognition methods, it is characterised in that：Determining human geometry's form is specific
Including：
Display foreground detection, matches with Gauss model and obtains background dot for each pixel in the area image to be measured,
The binary image about foreground area in the region to be measured is obtained according to the background dot；
Human figure differentiates；The binary image is successively carried out to graphics expansion processing, edge detection process and human body to know
Other places reason, obtains human geometry's appearance model.
4. safety cap as claimed in claim 3 wears recognition methods, it is characterised in that：The human figure also wraps before differentiating
Include the noise rejected in the binary image using the method for median filtering.
5. safety cap as claimed in claim 3 wears recognition methods, it is characterised in that：The edge detection process specifically includes
Edge detection is carried out to the human region in the binary image using Canny edge detection algorithm.
6. a kind of electronic equipment, it is characterised in that including：Processor；
Memory；And program, wherein described program is stored in the memory, and is configured to be held by processor
Row, described program include requiring method described in 1-5 any one for perform claim.
7. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that：The computer program quilt
Processor executes the method as described in claim 1-5 any one.
8. safety cap wears identifying system, it is characterised in that including：
Acquisition module, the acquisition module is for being acquired area image to be measured；
Human geometry's form determining module, human geometry's body determining module be used for using mixed Gauss model to it is described to
It surveys area image to carry out foreground detection processing and obtain the binary image of foreground area in the region to be measured, by the two-value
Change image to carry out human figure differentiation processing and obtain human geometry's appearance model；
Pixel characteristic extraction module, the pixel characteristic extraction module are used for the positional relationship according to human body safe wearing cap in institute
It states safety cap in the position in human geometry's appearance model and wears region, extract the pixel characteristic that the safety cap wears region；
Safety cap wears identification module, and the safety cap wears the pixel spy that identification module is used to wear the safety cap region
Sign is differentiated with default safety cap feature, if meeting default safety cap feature, is determined as safe wearing cap, if discontented
Foot, then be determined as non-safe wearing cap.
9. safety cap as claimed in claim 8 wears identifying system, it is characterised in that：It further include image pre-processing module, institute
Image pre-processing module is stated for carrying out image gray processing processing and image denoising processing to the area image to be measured.
10. safety cap as claimed in claim 8 wears identifying system, it is characterised in that：Human geometry's form determines mould
Block includes display foreground detection unit and human figure judgement unit, and described image foreground detection unit is used for will be described to be measured
Each pixel in area image matches with Gauss model and obtains background dot, according to the background dot obtain about it is described to
Survey the binary image of foreground area in region；The human figure judgement unit is for successively carrying out the binary image
Graphics expansion processing, edge detection process and human bioequivalence processing, obtain human geometry's appearance model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810392822.7A CN108921004A (en) | 2018-04-27 | 2018-04-27 | Safety cap wears recognition methods, electronic equipment, storage medium and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810392822.7A CN108921004A (en) | 2018-04-27 | 2018-04-27 | Safety cap wears recognition methods, electronic equipment, storage medium and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108921004A true CN108921004A (en) | 2018-11-30 |
Family
ID=64403890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810392822.7A Withdrawn CN108921004A (en) | 2018-04-27 | 2018-04-27 | Safety cap wears recognition methods, electronic equipment, storage medium and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108921004A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670441A (en) * | 2018-12-14 | 2019-04-23 | 广东亿迅科技有限公司 | A kind of realization safety cap wearing knows method for distinguishing, system, terminal and computer readable storage medium |
| CN109854923A (en) * | 2018-12-07 | 2019-06-07 | 国网河南省电力公司检修公司 | A kind of remote meter identifier of wear-type |
| CN109858367A (en) * | 2018-12-29 | 2019-06-07 | 华中科技大学 | The vision automated detection method and system that worker passes through support unsafe acts |
| CN110414342A (en) * | 2019-06-24 | 2019-11-05 | 台州宏达电力建设有限公司 | A kind of movement human detection recognition method based on video image processing technology |
| CN111079731A (en) * | 2019-12-03 | 2020-04-28 | 中冶赛迪重庆信息技术有限公司 | Configuration system, method, equipment and medium based on safety helmet identification monitoring system |
| CN112329554A (en) * | 2020-10-19 | 2021-02-05 | 通辽发电总厂有限责任公司 | Low-resolution image helmet identification method and device |
| CN113593178A (en) * | 2021-08-03 | 2021-11-02 | 安徽迪曙智能科技有限公司 | Visual field monitoring method with construction dynamic monitoring function |
| CN113743224A (en) * | 2021-08-04 | 2021-12-03 | 国网福建省电力有限公司信息通信分公司 | Ascending operator safety belt wearing monitoring method and system based on edge calculation |
| CN113971829A (en) * | 2021-10-28 | 2022-01-25 | 广东律诚工程咨询有限公司 | Intelligent detection method, device, equipment and storage medium for wearing condition of safety helmet |
-
2018
- 2018-04-27 CN CN201810392822.7A patent/CN108921004A/en not_active Withdrawn
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109854923A (en) * | 2018-12-07 | 2019-06-07 | 国网河南省电力公司检修公司 | A kind of remote meter identifier of wear-type |
| CN109670441A (en) * | 2018-12-14 | 2019-04-23 | 广东亿迅科技有限公司 | A kind of realization safety cap wearing knows method for distinguishing, system, terminal and computer readable storage medium |
| CN109670441B (en) * | 2018-12-14 | 2024-02-06 | 广东亿迅科技有限公司 | Method, system, terminal and computer readable storage medium for realizing wearing recognition of safety helmet |
| CN109858367A (en) * | 2018-12-29 | 2019-06-07 | 华中科技大学 | The vision automated detection method and system that worker passes through support unsafe acts |
| CN110414342A (en) * | 2019-06-24 | 2019-11-05 | 台州宏达电力建设有限公司 | A kind of movement human detection recognition method based on video image processing technology |
| CN111079731A (en) * | 2019-12-03 | 2020-04-28 | 中冶赛迪重庆信息技术有限公司 | Configuration system, method, equipment and medium based on safety helmet identification monitoring system |
| CN112329554A (en) * | 2020-10-19 | 2021-02-05 | 通辽发电总厂有限责任公司 | Low-resolution image helmet identification method and device |
| CN112329554B (en) * | 2020-10-19 | 2024-06-18 | 通辽第二发电有限责任公司 | Low-resolution image safety helmet identification method and device |
| CN113593178A (en) * | 2021-08-03 | 2021-11-02 | 安徽迪曙智能科技有限公司 | Visual field monitoring method with construction dynamic monitoring function |
| CN113743224A (en) * | 2021-08-04 | 2021-12-03 | 国网福建省电力有限公司信息通信分公司 | Ascending operator safety belt wearing monitoring method and system based on edge calculation |
| CN113743224B (en) * | 2021-08-04 | 2023-05-23 | 国网福建省电力有限公司信息通信分公司 | Method and system for monitoring wearing of safety belt of ascending operator based on edge calculation |
| CN113971829A (en) * | 2021-10-28 | 2022-01-25 | 广东律诚工程咨询有限公司 | Intelligent detection method, device, equipment and storage medium for wearing condition of safety helmet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921004A (en) | Safety cap wears recognition methods, electronic equipment, storage medium and system | |
| CN103034852B (en) | The detection method of particular color pedestrian under Still Camera scene | |
| CN110097034B (en) | Intelligent face health degree identification and evaluation method | |
| CN104036278B (en) | The extracting method of face algorithm standard rules face image | |
| CN101359365B (en) | Iris positioning method based on maximum between-class variance and gray scale information | |
| CN109490316A (en) | A kind of surface defects detection algorithm based on machine vision | |
| CN109087286A (en) | A kind of detection method and application based on Computer Image Processing and pattern-recognition | |
| CN107341790B (en) | A kind of image processing method of environment cleanliness detection | |
| Sobottka et al. | Looking for faces and facial features in color images | |
| CN113592861A (en) | Bridge crack detection method based on dynamic threshold | |
| CN106250936A (en) | Multiple features multithreading safety check contraband automatic identifying method based on machine learning | |
| CN101339603A (en) | Method for selecting qualified iris image from video frequency stream | |
| CN107610104A (en) | Crack detecting method at a kind of elevator compensation chain R based on machine vision | |
| CN110348461A (en) | A kind of Surface Flaw feature extracting method | |
| Duan et al. | A WBC segmentation methord based on HSI color space | |
| CN109543518A (en) | A kind of human face precise recognition method based on integral projection | |
| CN111553214B (en) | Method and system for detecting smoking behavior of driver | |
| CN113935666B (en) | Building decoration wall tile abnormity evaluation method based on image processing | |
| CN106203338B (en) | Human eye state method for quickly identifying based on net region segmentation and threshold adaptive | |
| CN109255326A (en) | A kind of traffic scene smog intelligent detecting method based on multidimensional information Fusion Features | |
| CN108335294A (en) | The power distribution room abnormality image-recognizing method of complex condition | |
| CN108108740B (en) | Active millimeter wave human body image gender identification method | |
| CN103049788A (en) | Computer-vision-based system and method for detecting number of pedestrians waiting to cross crosswalk | |
| CN104715459B (en) | Blood-vessel image Enhancement Method | |
| CN113221881A (en) | Multi-level smart phone screen defect detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181130 |
|
| WW01 | Invention patent application withdrawn after publication |